Security audit
本象协议 Benxiang Protocol
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for a project-state protocol, with disclosed local persistence and no hidden code or automatic high-impact behavior in the artifact.
Install only from the intended repository, review the code behind the referenced node commands before use, and run the MCP server only against .origin packages whose project state you are comfortable exposing to connected agents.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.